Node succeds in upscaling images but not video.
Node installed from manager.
Environment
OS: WSL2 Linux Ubuntu 24.04
Python: 3.12
CUDA: 13.0
NVIDIA Driver: 595
ComfyUI: 3.39.2
nvidia-smi:
(base) aa@aadesktop:~$ nvidia-smi
Thu Mar 12 12:02:28 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.54 Driver Version: 595.79 CUDA Version: 13.2 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 5090 On | 00000000:01:00.0 On | N/A |
| 38% 49C P8 24W / 575W | 28038MiB / 32607MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3348 C /python3.12 N/A |
| 0 N/A N/A 4173 C /python3.13 N/A |
+-----------------------------------------------------------------------------------------+
(base) aa@aadesktop:~$
Reproduction:
video upload node > images > vfx upscale (this node) any quality and any upscale ratio > following error:
got prompt
RTX Video Super Resolution is unavailable (NvVFX_Load failed: An otherwise unspecified error has occurred (code -1)). This is typically caused by a driver/NGX SDK version mismatch. On WSL2, update your Windows NVIDIA driver to the latest version and restart WSL. Falling back to bicubic upscaling.
Prompt executed in 19.21 seconds
comfyui logs:
(cu128) aa@aadesktop:~$ CUDA_LAUNCH_BLOCKING=1 python ./ComfyUI/main.py --listen --enable-cors-header --use-sage-attention --max-upload-size 1000 --preview-method latent2rgb --port 8189
[START] Security scan
[ComfyUI-Manager] Using uv as Python module for pip operations.
Using Python 3.12.12 environment at: miniconda3/envs/cu128
[DONE] Security scan
ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-03-12 12:07:08.207
** Platform: Linux
** Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
** Python executable: /home/aa/miniconda3/envs/cu128/bin/python
** ComfyUI Path: /home/aa/ComfyUI
** ComfyUI Base Folder Path: /home/aa/ComfyUI
** User directory: /home/aa/ComfyUI/user
** ComfyUI-Manager config path: /home/aa/ComfyUI/user/__manager/config.ini
** Log path: /home/aa/ComfyUI/user/comfyui.log
Using Python 3.12.12 environment at: miniconda3/envs/cu128
Using Python 3.12.12 environment at: miniconda3/envs/cu128
[comfy-env] ComfyUI-GeometryPack: root config found but env not built yet
[comfy-env] prestartup complete
[GeometryPack] Parsed GeomPackRemesh: 6 backends
[GeometryPack] Parsed GeomPackFillHoles: 2 backends
[GeometryPack] Generated backend_mappings.json
[GeometryPack] All assets already exist in /home/aa/ComfyUI/input/3d
[SAM3DBody] Running prestartup script...
[SAM3DBody] viewer_fbx.html is up to date
[SAM3DBody] viewer-bundle.js is up to date
[SAM3DBody] mesh_preview_fbx.js is up to date
[SAM3DBody] Skipped 4 existing asset file(s)
[SAM3DBody] Prestartup script completed
[comfy-env] ComfyUI-TRELLIS2: root config found but env not built yet
[comfy-env] prestartup complete
[comfy-env] ComfyUI-MotionCapture: root config found but env not built yet
[comfy-env] 1 isolation env(s):
[comfy-env] _env_618b92 -> /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture/nodes/_env_618b92
[comfy-env] prestartup complete
[comfy-env] comfyui-sam3: root config found but env not built yet
[comfy-env] prestartup complete
Prestartup times for custom nodes:
0.0 seconds: /home/aa/ComfyUI/custom_nodes/rgthree-comfy
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SAM3DBody
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-geometrypack
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-sam3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-TRELLIS2
0.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Manager
1.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GeometryPack
WARNING: Potential Error in code: Torch already imported, torch should never be imported before this point.
WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Checkpoint files will always be loaded safely.
Total VRAM 32607 MB, total RAM 117914 MB
pytorch version: 2.10.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 112018.0
working around nvidia conv3d memory bug.
Using sage attention
Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
ComfyUI version: 0.16.4
comfy-aimdo version: 0.2.9
comfy-kitchen version: 0.2.7
ComfyUI frontend version: 1.41.16
[Prompt Server] web root: /home/aa/miniconda3/envs/cu128/lib/python3.12/site-packages/comfyui_frontend_package/static
Asset seeder disabled
Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
ComfyUI Version: v0.16.4-19-g8f9ea495 | Released on '2026-03-12'
Web extensions folder found at /home/aa/ComfyUI/web/extensions/ComfyLiterals
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
🔧 torchaudio.save/load globally patched (scipy for WAV files, no TorchCodec)
🔇 Suppressed torchaudio 2.9 migration warnings
ℹ️ Critical package versions: NumPy 1.26.4, Librosa 0.11.0, Numba 0.63.1, PyTorch 2.10.0+cu128, TorchAudio 2.10.0+cu128, Transformers 5.3.0, Accelerate 1.13.0, SoundFile 0.13.1
⚠️ Transformers 5.x detected: Qwen3-TTS tokenizer is incompatible.
Please downgrade to transformers<=4.57.3 (see requirements.txt).
❌ Voice Capture failed: PortAudio library not found
❌ Vocal/Noise Removal failed: No module named 'audio_separator'
🚀 TTS Audio Suite v4.21.17
Universal multi-engine TTS extension for ComfyUI
✅ TTS Audio Suite v4.21.17 loaded with 33 nodes:
• ⚙️ ChatterBox Official 23-Lang Engine
• ⚙️ ChatterBox TTS Engine
• ⚙️ CosyVoice3 Engine
• ⚙️ F5 TTS Engine
• ⚙️ Higgs Audio 2 Engine
• ⚙️ IndexTTS-2 Engine
• ⚙️ Qwen3-TTS Engine
• ⚙️ RVC Engine
• ⚙️ Step Audio EditX Engine
• ⚙️ VibeVoice Engine
• ♻️ Refresh Voice Cache
• ✏️ ASR Transcribe
• 🌈 IndexTTS-2 Emotion Vectors
• 🌈 IndexTTS-2 Text Emotion
• 🌊 Audio Wave Analyzer
• 🎤 TTS Text
• 🎨 Qwen3-TTS Voice Designer
• 🎨 Step Audio EditX - Audio Editor
• 🎭 Character Voices
• 🎭 Load RVC Character Model
• 🏷️ Multiline TTS Tag Editor
• 👄 F5-TTS Speech Editor
• 📝 Phoneme Text Normalizer
• 📺 TTS SRT
• 🔄 Voice Changer
• 🔧 ASR SRT Advanced Options
• 🔧 Audio Analyzer Options
• 🔧 F5-TTS Edit Options
• 🔧 RVC Pitch Extraction Options
• 🔧 Viseme Mouth Shape Options
• 🗣️ Silent Speech Analyzer
• 🤐 Voice Fixer
• 🥪 Merge Audio
[geompack] loading...
[geompack] calling register_nodes
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (root)...
[comfy-env] Imported nodes root: 0 nodes
[comfy-env] Importing blender...
[comfy-env] Imported blender: 5 nodes
[comfy-env] Importing gpu...
[comfy-env] Imported gpu: 1 nodes
[comfy-env] Importing main...
[TTS Audio Suite] 🎭 Character voices: Found 29 characters, 10 aliases (cached)
[TTS Audio Suite] 🔄 Updating character discovery in background...
[comfy-env] Imported main: 57 nodes
[comfy-env] No env for blender -- run 'comfy-env install'
[comfy-env] No env for main -- run 'comfy-env install'
[comfy-env] No env for gpu -- run 'comfy-env install'
[comfy-env] Registered 63 total nodes
Comfyroll Studio v1.76 : 175 Nodes Loaded
ComfyUI-Env-Manager v0.1.0 routes registered
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ckpts path: /home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux/ckpts
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using symlinks: False
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly
warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly")
Loading faiss with AVX512 support.
Successfully loaded faiss with AVX512 support.
📋 System Dependencies (background check):
⚠️ Engine dependencies missing:
ChatterBox TTS:
• s3tokenizer (import: s3tokenizer)
F5-TTS:
• cached-path (import: cached_path)
Higgs Audio 2:
• descript-audio-codec (import: dac)
• vector-quantize-pytorch (import: vector_quantize_pytorch)
RVC Voice Conversion:
• torchcrepe (import: torchcrepe)
🔧 Fix: pip install -r requirements.txt
ℹ️ Engine nodes will fail without dependencies
[ComfyUI-Easy-Use] server: v1.3.4 Loaded
[ComfyUI-Easy-Use] web root: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use/web_version/v2 Loaded
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/virtuoso-nodes/init.py", line 1, in
from .blendmodes import BlendModes
File "/home/aa/ComfyUI/custom_nodes/virtuoso-nodes/blendmodes.py", line 10, in
from blend_modes import grain_extract, grain_merge
ModuleNotFoundError: No module named 'blend_modes'
Cannot import /home/aa/ComfyUI/custom_nodes/virtuoso-nodes module for custom nodes: No module named 'blend_modes'
ComfyUI-Multiband loaded: 15 nodes registered
⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
💡 Optional: pip install flash-attn
🔧 Conv3d workaround active: PyTorch 2.10.0, cuDNN 91002 (fixing VAE 3x memory bug)
📊 Initial CUDA memory: 30.15GB free / 31.84GB total
FETCH ComfyRegistry Data: 5/130
[GeomPack] CGAL Python package found - CGAL Isotropic Remesh node available
[GeomPack] Custom server routes registered
[SAM3DBody] Initializing ComfyUI-SAM3DBody custom nodes...
[SAM3DBody] [OK] Loaded 15 node(s)
[SAM3DBody] - LoadSAM3DBodyModel
[SAM3DBody] - SAM3DBodyAddMeshToSkeleton
[SAM3DBody] - SAM3DBodyExportFBX
[SAM3DBody] - SAM3DBodyExportMesh
[SAM3DBody] - SAM3DBodyExportMultipleFBX
[SAM3DBody] - SAM3DBodyGetVertices
[SAM3DBody] - SAM3DBodyLoadMesh
[SAM3DBody] - SAM3DBodyLoadSkeleton
[SAM3DBody] - SAM3DBodyPreviewRiggedMesh
[SAM3DBody] - SAM3DBodyProcess
[SAM3DBody] - SAM3DBodyProcessAdvanced
[SAM3DBody] - SAM3DBodyProcessMultiple
[SAM3DBody] - SAM3DBodySaveSkeleton
[SAM3DBody] - SAM3DBodySelectMesh
[SAM3DBody] - SAM3DBodyVisualize
[SAM3DBody] Registered server routes:
[SAM3DBody] POST /sam3d/save_glb
[SAM3DBody] POST /sam3d/export_posed_fbx
[SAM3DBody] GET /sam3d/mesh_files
[SAM3DBody] [OK] Server routes registered
[SAM3DBody] Initialization complete
Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
AA Nodes loaded: ['MultiImageUploadIterator', 'ImageBatchIterator', 'BatchQueueManager', 'BatchImageProcessor', 'FolderImageIterator']
[Impact Pack] Wildcards loading done.
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: AzureExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
[rgthree-comfy] Loaded 48 exciting nodes. 🎉
[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
loading...
calling register_nodes
registered TRELLIS2 model configs with ComfyUI
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (root)...
[comfy-env] Imported nodes root: 17 nodes
[comfy-env] No env for ComfyUI-TRELLIS2 -- run 'comfy-env install'
[comfy-env] No env for nodes -- run 'comfy-env install'
[comfy-env] Registered 17 total nodes
loading...
calling register_nodes
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (isolation root)...
[comfy-env] Cache hit for nodes: 22 nodes
[comfy-env] Imported nodes root: 22 nodes (isolation)
[comfy-env] Registered 22 total nodes
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt/init.py", line 6, in
from .trt_utilities import Engine
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt/trt_utilities.py", line 22, in
from polygraphy.backend.common import bytes_from_path
ModuleNotFoundError: No module named 'polygraphy'
Cannot import /home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt module for custom nodes: No module named 'polygraphy'
[ComfyUI-DepthAnythingV3] Initializing custom node...
[ComfyUI-DepthAnythingV3] [WARNING] Failed to import node classes: No module named 'addict'
[ComfyUI-DepthAnythingV3] Traceback:
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/init.py", line 23, in
from .nodes import (
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/init.py", line 12, in
from .nodes_loader import (
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_loader.py", line 11, in
from .depth_anything_v3.model.da3 import DepthAnything3Net, NestedDepthAnything3Net
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model/da3.py", line 19, in
from addict import Dict
ModuleNotFoundError: No module named 'addict'
[ComfyUI-DepthAnythingV3] [ERROR] Failed to load (1 error(s)):
-
Failed to import node classes: No module named 'addict'
[ComfyUI-DepthAnythingV3] Please check the errors above and your installation.
ComfyUI-GGUF: Allowing full torch compile
[Z-Image] Init - DIFFSYNTH_MODEL_BASE_PATH: None
[WAS LMStudio Easy-Query] has loaded 8 nodes.
Nodes: LM Studio Model, LM Studio Query, LM Studio Easy-Caption, LM Studio Chat, LM Studio Options, WAS Load Image Directory, LM Studio Easy-Caption Dataset, LM Studio Caption Dataset
[/home/aa/ComfyUI/custom_nodes/comfy-mtb] | INFO -> loaded 103 nodes successfuly
[/home/aa/ComfyUI/custom_nodes/comfy-mtb] | INFO -> Some nodes (5) could not be loaded. This can be ignored, but go to http://0.0.0.0,:::8189/mtb if you want more information.
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: ffmpeg_bin_path is not set in /home/aa/ComfyUI/custom_nodes/was-ns/was_suite_config.json config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 220 nodes successfully.
"Success is not in what you have, but who you are." - Bo Bennett
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 11, in
from spas_sage_attn import block_sparse_sage2_attn_cuda
ModuleNotFoundError: No module named 'spas_sage_attn'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 14, in
from sparse_sageattn import sparse_sageattn as block_sparse_sage2_attn_cuda
ModuleNotFoundError: No module named 'sparse_sageattn'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/radialattn/init.py", line 1, in
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/radialattn/nodes.py", line 9, in
from .attn_mask import MaskMap, RadialAttention
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 16, in
raise RuntimeError("Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn")
RuntimeError: Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn
Cannot import /home/aa/ComfyUI/custom_nodes/radialattn module for custom nodes: Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn
ComfyUI-Multiband loaded: 15 nodes registered
Total VRAM 32607 MB, total RAM 117914 MB
pytorch version: 2.10.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 112018.0
SDPose Node: CRITICAL ERROR
Failed to import internal modules (e.g., models.HeatmapHead).
This almost always means the 'models', 'pipelines', or 'mmpose' sub-folders are missing or installed incorrectly.
Please ensure the node was installed completely (including all sub-folders).
Original error: No module named 'mmcv'
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/init.py", line 2, in
from .sdpose_ood_nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/sdpose_ood_nodes.py", line 87, in
raise e
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/sdpose_ood_nodes.py", line 76, in
from .models.HeatmapHead import get_heatmap_head
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/models/HeatmapHead.py", line 10, in
from mmpose.registry import MODELS
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/mmpose/init.py", line 7, in
import mmcv
ModuleNotFoundError: No module named 'mmcv'
Cannot import /home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD module for custom nodes: No module named 'mmcv'
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/init.py", line 1, in
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/init.py", line 3, in
from .save_surreal import SaveJsonToSurreal, SaveTextToSurreal
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/save_surreal.py", line 1, in
from .surreal import surreal_connect
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/surreal.py", line 1, in
from surrealist import Surreal
ModuleNotFoundError: No module named 'surrealist'
Cannot import /home/aa/ComfyUI/custom_nodes/comfyui-tensorops module for custom nodes: No module named 'surrealist'
Import times for custom nodes:
0.0 seconds: /home/aa/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Yedp-Action-Director
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyLiterals
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-CameraPack
0.0 seconds: /home/aa/ComfyUI/custom_nodes/aa_comfyui_nodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_Make-It-Animatable
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Env-Manager
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/virtuoso-nodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SCAIL-Pose
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-inpaint-cropandstitch
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-wd14-tagger
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/radialattn
0.0 seconds: /home/aa/ComfyUI/custom_nodes/cg-image-filter
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GGUF
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-CacheDiT
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/comfyui-tensorops
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Wan-VACE-Prep
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-various
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-WanAnimatePreprocess
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_LMStudio_EasyQuery
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_essentials
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyMath
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-custom-scripts
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-sam3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/steerable-motion
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-multiband
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-frame-interpolation
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SAM3DBody
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-dream-video-batches
0.0 seconds: /home/aa/ComfyUI/custom_nodes/vnccs
0.0 seconds: /home/aa/ComfyUI/custom_nodes/basic_data_handling
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Multiband
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_VNCCS_Utils
0.0 seconds: /home/aa/ComfyUI/custom_nodes/rgthree-comfy
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_essentials
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MelBandRoFormer
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-LTXVideo
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-KJNodes
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-TRELLIS2
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_DSS_Wrapper
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfy-mtb
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_nvidia_rtx_nodes
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-videohelpersuite
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-impact-pack
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper
0.2 seconds: /home/aa/ComfyUI/custom_nodes/tts_audio_suite
0.3 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
0.3 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-geometrypack
0.6 seconds: /home/aa/ComfyUI/custom_nodes/seedvr2_videoupscaler
0.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GeometryPack
0.7 seconds: /home/aa/ComfyUI/custom_nodes/was-ns
0.9 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-HyMotion
1.7 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Starting server
To see the GUI go to: http://0.0.0.0:8189
To see the GUI go to: http://[::]:8189
FETCH ComfyRegistry Data: 10/130
FETCH ComfyRegistry Data: 15/130
FETCH ComfyRegistry Data: 20/130
FETCH ComfyRegistry Data: 25/130
FETCH ComfyRegistry Data: 30/130
FETCH ComfyRegistry Data: 35/130
FETCH ComfyRegistry Data: 40/130
FETCH ComfyRegistry Data: 45/130
FETCH ComfyRegistry Data: 50/130
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
{"client": "<lmstudio.sync_api.Client object at 0x77124827f980>", "event": "Websocket handling thread started", "thread_id": "Thread-8"}
Error fetching models: LM Studio is not reachable at any default port. Is LM Studio running?
Error fetching models: Local API host port is not yet resolved.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
🔧 Settings endpoint called
🔧 Received settings: precision=auto, device=auto, vc_engine=chatterbox_23lang, cosyvoice_variant=RL
🎨 Step Audio EditX inline tags: precision=auto, device=auto
🔄 Voice restoration engine: chatterbox_23lang
FETCH ComfyRegistry Data: 55/130
FETCH ComfyRegistry Data: 60/130
FETCH ComfyRegistry Data: 65/130
FETCH ComfyRegistry Data: 70/130
FETCH ComfyRegistry Data: 75/130
FETCH ComfyRegistry Data: 80/130
FETCH ComfyRegistry Data: 85/130
FETCH ComfyRegistry Data: 90/130
FETCH ComfyRegistry Data: 95/130
FETCH ComfyRegistry Data: 100/130
FETCH ComfyRegistry Data: 105/130
FETCH ComfyRegistry Data: 110/130
FETCH ComfyRegistry Data: 115/130
FETCH ComfyRegistry Data: 120/130
FETCH ComfyRegistry Data: 125/130
FETCH ComfyRegistry Data: 130/130
got prompt
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
RTX Video Super Resolution is unavailable (NvVFX_Load failed: An otherwise unspecified error has occurred (code -1)). This is typically caused by a driver/NGX SDK version mismatch. On WSL2, update your Windows NVIDIA driver to the latest version and restart WSL. Falling back to bicubic upscaling.
Node succeds in upscaling images but not video.
Node installed from manager.
Environment
OS: WSL2 Linux Ubuntu 24.04
Python: 3.12
CUDA: 13.0
NVIDIA Driver: 595
ComfyUI: 3.39.2
nvidia-smi:
(base) aa@aadesktop:~$ nvidia-smi
Thu Mar 12 12:02:28 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.54 Driver Version: 595.79 CUDA Version: 13.2 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 5090 On | 00000000:01:00.0 On | N/A |
| 38% 49C P8 24W / 575W | 28038MiB / 32607MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3348 C /python3.12 N/A |
| 0 N/A N/A 4173 C /python3.13 N/A |
+-----------------------------------------------------------------------------------------+
(base) aa@aadesktop:~$
Reproduction:
video upload node > images > vfx upscale (this node) any quality and any upscale ratio > following error:
got prompt
RTX Video Super Resolution is unavailable (NvVFX_Load failed: An otherwise unspecified error has occurred (code -1)). This is typically caused by a driver/NGX SDK version mismatch. On WSL2, update your Windows NVIDIA driver to the latest version and restart WSL. Falling back to bicubic upscaling.
Prompt executed in 19.21 seconds
comfyui logs:
(cu128) aa@aadesktop:~$ CUDA_LAUNCH_BLOCKING=1 python ./ComfyUI/main.py --listen --enable-cors-header --use-sage-attention --max-upload-size 1000 --preview-method latent2rgb --port 8189
[START] Security scan
[ComfyUI-Manager] Using
uvas Python module for pip operations.Using Python 3.12.12 environment at: miniconda3/envs/cu128
[DONE] Security scan
ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-03-12 12:07:08.207
** Platform: Linux
** Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
** Python executable: /home/aa/miniconda3/envs/cu128/bin/python
** ComfyUI Path: /home/aa/ComfyUI
** ComfyUI Base Folder Path: /home/aa/ComfyUI
** User directory: /home/aa/ComfyUI/user
** ComfyUI-Manager config path: /home/aa/ComfyUI/user/__manager/config.ini
** Log path: /home/aa/ComfyUI/user/comfyui.log
Using Python 3.12.12 environment at: miniconda3/envs/cu128
Using Python 3.12.12 environment at: miniconda3/envs/cu128
[comfy-env] ComfyUI-GeometryPack: root config found but env not built yet
[comfy-env] prestartup complete
[GeometryPack] Parsed GeomPackRemesh: 6 backends
[GeometryPack] Parsed GeomPackFillHoles: 2 backends
[GeometryPack] Generated backend_mappings.json
[GeometryPack] All assets already exist in /home/aa/ComfyUI/input/3d
[SAM3DBody] Running prestartup script...
[SAM3DBody] viewer_fbx.html is up to date
[SAM3DBody] viewer-bundle.js is up to date
[SAM3DBody] mesh_preview_fbx.js is up to date
[SAM3DBody] Skipped 4 existing asset file(s)
[SAM3DBody] Prestartup script completed
[comfy-env] ComfyUI-TRELLIS2: root config found but env not built yet
[comfy-env] prestartup complete
[comfy-env] ComfyUI-MotionCapture: root config found but env not built yet
[comfy-env] 1 isolation env(s):
[comfy-env] _env_618b92 -> /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture/nodes/_env_618b92
[comfy-env] prestartup complete
[comfy-env] comfyui-sam3: root config found but env not built yet
[comfy-env] prestartup complete
Prestartup times for custom nodes:
0.0 seconds: /home/aa/ComfyUI/custom_nodes/rgthree-comfy
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SAM3DBody
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-geometrypack
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-sam3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-TRELLIS2
0.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Manager
1.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GeometryPack
WARNING: Potential Error in code: Torch already imported, torch should never be imported before this point.
WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Checkpoint files will always be loaded safely.
Total VRAM 32607 MB, total RAM 117914 MB
pytorch version: 2.10.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 112018.0
working around nvidia conv3d memory bug.
Using sage attention
Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
ComfyUI version: 0.16.4
comfy-aimdo version: 0.2.9
comfy-kitchen version: 0.2.7
ComfyUI frontend version: 1.41.16
[Prompt Server] web root: /home/aa/miniconda3/envs/cu128/lib/python3.12/site-packages/comfyui_frontend_package/static
Asset seeder disabled
Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
ComfyUI Version: v0.16.4-19-g8f9ea495 | Released on '2026-03-12'
Web extensions folder found at /home/aa/ComfyUI/web/extensions/ComfyLiterals
⚠️ Transformers 5.x detected: Qwen3-TTS tokenizer is incompatible.
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
🔧 torchaudio.save/load globally patched (scipy for WAV files, no TorchCodec)
🔇 Suppressed torchaudio 2.9 migration warnings
ℹ️ Critical package versions: NumPy 1.26.4, Librosa 0.11.0, Numba 0.63.1, PyTorch 2.10.0+cu128, TorchAudio 2.10.0+cu128, Transformers 5.3.0, Accelerate 1.13.0, SoundFile 0.13.1
Please downgrade to transformers<=4.57.3 (see requirements.txt).
❌ Voice Capture failed: PortAudio library not found
❌ Vocal/Noise Removal failed: No module named 'audio_separator'
🚀 TTS Audio Suite v4.21.17
Universal multi-engine TTS extension for ComfyUI
✅ TTS Audio Suite v4.21.17 loaded with 33 nodes:
• ⚙️ ChatterBox Official 23-Lang Engine
• ⚙️ ChatterBox TTS Engine
• ⚙️ CosyVoice3 Engine
• ⚙️ F5 TTS Engine
• ⚙️ Higgs Audio 2 Engine
• ⚙️ IndexTTS-2 Engine
• ⚙️ Qwen3-TTS Engine
• ⚙️ RVC Engine
• ⚙️ Step Audio EditX Engine
• ⚙️ VibeVoice Engine
• ♻️ Refresh Voice Cache
• ✏️ ASR Transcribe
• 🌈 IndexTTS-2 Emotion Vectors
• 🌈 IndexTTS-2 Text Emotion
• 🌊 Audio Wave Analyzer
• 🎤 TTS Text
• 🎨 Qwen3-TTS Voice Designer
• 🎨 Step Audio EditX - Audio Editor
• 🎭 Character Voices
• 🎭 Load RVC Character Model
• 🏷️ Multiline TTS Tag Editor
• 👄 F5-TTS Speech Editor
• 📝 Phoneme Text Normalizer
• 📺 TTS SRT
• 🔄 Voice Changer
• 🔧 ASR SRT Advanced Options
• 🔧 Audio Analyzer Options
• 🔧 F5-TTS Edit Options
• 🔧 RVC Pitch Extraction Options
• 🔧 Viseme Mouth Shape Options
• 🗣️ Silent Speech Analyzer
• 🤐 Voice Fixer
• 🥪 Merge Audio
[geompack] loading...
[geompack] calling register_nodes
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (root)...
[comfy-env] Imported nodes root: 0 nodes
[comfy-env] Importing blender...
[comfy-env] Imported blender: 5 nodes
[comfy-env] Importing gpu...
[comfy-env] Imported gpu: 1 nodes
[comfy-env] Importing main...
[TTS Audio Suite] 🎭 Character voices: Found 29 characters, 10 aliases (cached)
[TTS Audio Suite] 🔄 Updating character discovery in background...
[comfy-env] Imported main: 57 nodes
[comfy-env] No env for blender -- run 'comfy-env install'
[comfy-env] No env for main -- run 'comfy-env install'
[comfy-env] No env for gpu -- run 'comfy-env install'
[comfy-env] Registered 63 total nodes
Comfyroll Studio v1.76 : 175 Nodes Loaded
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
ComfyUI-Env-Manager v0.1.0 routes registered
⚠️ Engine dependencies missing:
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ckpts path: /home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux/ckpts
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using symlinks: False
[/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
/home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly
warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly")
Loading faiss with AVX512 support.
Successfully loaded faiss with AVX512 support.
📋 System Dependencies (background check):
ChatterBox TTS:
• s3tokenizer (import: s3tokenizer)
F5-TTS:
• cached-path (import: cached_path)
Higgs Audio 2:
• descript-audio-codec (import: dac)
• vector-quantize-pytorch (import: vector_quantize_pytorch)
RVC Voice Conversion:
• torchcrepe (import: torchcrepe)
🔧 Fix: pip install -r requirements.txt
ℹ️ Engine nodes will fail without dependencies
[ComfyUI-Easy-Use] server: v1.3.4 Loaded
[ComfyUI-Easy-Use] web root: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use/web_version/v2 Loaded
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/virtuoso-nodes/init.py", line 1, in
from .blendmodes import BlendModes
File "/home/aa/ComfyUI/custom_nodes/virtuoso-nodes/blendmodes.py", line 10, in
from blend_modes import grain_extract, grain_merge
ModuleNotFoundError: No module named 'blend_modes'
Cannot import /home/aa/ComfyUI/custom_nodes/virtuoso-nodes module for custom nodes: No module named 'blend_modes'
ComfyUI-Multiband loaded: 15 nodes registered
⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
💡 Optional: pip install flash-attn
🔧 Conv3d workaround active: PyTorch 2.10.0, cuDNN 91002 (fixing VAE 3x memory bug)
📊 Initial CUDA memory: 30.15GB free / 31.84GB total
FETCH ComfyRegistry Data: 5/130
[GeomPack] CGAL Python package found - CGAL Isotropic Remesh node available
[GeomPack] Custom server routes registered
[SAM3DBody] Initializing ComfyUI-SAM3DBody custom nodes...
[SAM3DBody] [OK] Loaded 15 node(s)
[SAM3DBody] - LoadSAM3DBodyModel
[SAM3DBody] - SAM3DBodyAddMeshToSkeleton
[SAM3DBody] - SAM3DBodyExportFBX
[SAM3DBody] - SAM3DBodyExportMesh
[SAM3DBody] - SAM3DBodyExportMultipleFBX
[SAM3DBody] - SAM3DBodyGetVertices
[SAM3DBody] - SAM3DBodyLoadMesh
[SAM3DBody] - SAM3DBodyLoadSkeleton
[SAM3DBody] - SAM3DBodyPreviewRiggedMesh
[SAM3DBody] - SAM3DBodyProcess
[SAM3DBody] - SAM3DBodyProcessAdvanced
[SAM3DBody] - SAM3DBodyProcessMultiple
[SAM3DBody] - SAM3DBodySaveSkeleton
[SAM3DBody] - SAM3DBodySelectMesh
[SAM3DBody] - SAM3DBodyVisualize
[SAM3DBody] Registered server routes:
[SAM3DBody] POST /sam3d/save_glb
[SAM3DBody] POST /sam3d/export_posed_fbx
[SAM3DBody] GET /sam3d/mesh_files
[SAM3DBody] [OK] Server routes registered
[SAM3DBody] Initialization complete
Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
AA Nodes loaded: ['MultiImageUploadIterator', 'ImageBatchIterator', 'BatchQueueManager', 'BatchImageProcessor', 'FolderImageIterator']
[Impact Pack] Wildcards loading done.
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: AzureExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
[rgthree-comfy] Loaded 48 exciting nodes. 🎉
[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
loading...
calling register_nodes
registered TRELLIS2 model configs with ComfyUI
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (root)...
[comfy-env] Imported nodes root: 17 nodes
[comfy-env] No env for ComfyUI-TRELLIS2 -- run 'comfy-env install'
[comfy-env] No env for nodes -- run 'comfy-env install'
[comfy-env] Registered 17 total nodes
loading...
calling register_nodes
[comfy-env] Version: 0.2.11
[comfy-env] Importing nodes (isolation root)...
[comfy-env] Cache hit for nodes: 22 nodes
[comfy-env] Imported nodes root: 22 nodes (isolation)
[comfy-env] Registered 22 total nodes
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt/init.py", line 6, in
from .trt_utilities import Engine
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt/trt_utilities.py", line 22, in
from polygraphy.backend.common import bytes_from_path
ModuleNotFoundError: No module named 'polygraphy'
Cannot import /home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt module for custom nodes: No module named 'polygraphy'
[ComfyUI-DepthAnythingV3] Initializing custom node...
[ComfyUI-DepthAnythingV3] [WARNING] Failed to import node classes: No module named 'addict'
[ComfyUI-DepthAnythingV3] Traceback:
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/init.py", line 23, in
from .nodes import (
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/init.py", line 12, in
from .nodes_loader import (
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_loader.py", line 11, in
from .depth_anything_v3.model.da3 import DepthAnything3Net, NestedDepthAnything3Net
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model/da3.py", line 19, in
from addict import Dict
ModuleNotFoundError: No module named 'addict'
[ComfyUI-DepthAnythingV3] [ERROR] Failed to load (1 error(s)):
Failed to import node classes: No module named 'addict'
[ComfyUI-DepthAnythingV3] Please check the errors above and your installation.
ComfyUI-GGUF: Allowing full torch compile
[Z-Image] Init - DIFFSYNTH_MODEL_BASE_PATH: None
[WAS LMStudio Easy-Query] has loaded 8 nodes.
Nodes: LM Studio Model, LM Studio Query, LM Studio Easy-Caption, LM Studio Chat, LM Studio Options, WAS Load Image Directory, LM Studio Easy-Caption Dataset, LM Studio Caption Dataset
[/home/aa/ComfyUI/custom_nodes/comfy-mtb] | INFO -> loaded 103 nodes successfuly
[/home/aa/ComfyUI/custom_nodes/comfy-mtb] | INFO -> Some nodes (5) could not be loaded. This can be ignored, but go to http://0.0.0.0,:::8189/mtb if you want more information.
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning:
ffmpeg_bin_pathis not set in/home/aa/ComfyUI/custom_nodes/was-ns/was_suite_config.jsonconfig file. Will attempt to use system ffmpeg binaries if available.WAS Node Suite: Finished. Loaded 220 nodes successfully.
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 11, in
from spas_sage_attn import block_sparse_sage2_attn_cuda
ModuleNotFoundError: No module named 'spas_sage_attn'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 14, in
from sparse_sageattn import sparse_sageattn as block_sparse_sage2_attn_cuda
ModuleNotFoundError: No module named 'sparse_sageattn'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/radialattn/init.py", line 1, in
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/radialattn/nodes.py", line 9, in
from .attn_mask import MaskMap, RadialAttention
File "/home/aa/ComfyUI/custom_nodes/radialattn/attn_mask.py", line 16, in
raise RuntimeError("Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn")
RuntimeError: Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn
Cannot import /home/aa/ComfyUI/custom_nodes/radialattn module for custom nodes: Failed to import spas_sage_attn. Please install it following the instructions at https://github.com/woct0rdho/SpargeAttn
ComfyUI-Multiband loaded: 15 nodes registered
Total VRAM 32607 MB, total RAM 117914 MB
pytorch version: 2.10.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 112018.0
SDPose Node: CRITICAL ERROR
Failed to import internal modules (e.g., models.HeatmapHead).
This almost always means the 'models', 'pipelines', or 'mmpose' sub-folders are missing or installed incorrectly.
Please ensure the node was installed completely (including all sub-folders).
Original error: No module named 'mmcv'
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/init.py", line 2, in
from .sdpose_ood_nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/sdpose_ood_nodes.py", line 87, in
raise e
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/sdpose_ood_nodes.py", line 76, in
from .models.HeatmapHead import get_heatmap_head
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/models/HeatmapHead.py", line 10, in
from mmpose.registry import MODELS
File "/home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD/mmpose/init.py", line 7, in
import mmcv
ModuleNotFoundError: No module named 'mmcv'
Cannot import /home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD module for custom nodes: No module named 'mmcv'
Traceback (most recent call last):
File "/home/aa/ComfyUI/nodes.py", line 2223, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 999, in exec_module
File "", line 488, in _call_with_frames_removed
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/init.py", line 1, in
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/init.py", line 3, in
from .save_surreal import SaveJsonToSurreal, SaveTextToSurreal
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/save_surreal.py", line 1, in
from .surreal import surreal_connect
File "/home/aa/ComfyUI/custom_nodes/comfyui-tensorops/nodes/surreal.py", line 1, in
from surrealist import Surreal
ModuleNotFoundError: No module named 'surrealist'
Cannot import /home/aa/ComfyUI/custom_nodes/comfyui-tensorops module for custom nodes: No module named 'surrealist'
Import times for custom nodes:
0.0 seconds: /home/aa/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Yedp-Action-Director
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyLiterals
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-CameraPack
0.0 seconds: /home/aa/ComfyUI/custom_nodes/aa_comfyui_nodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_Make-It-Animatable
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Env-Manager
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/virtuoso-nodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SCAIL-Pose
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-inpaint-cropandstitch
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-wd14-tagger
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/ComfyUI-Upscaler-Tensorrt
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/radialattn
0.0 seconds: /home/aa/ComfyUI/custom_nodes/cg-image-filter
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GGUF
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-CacheDiT
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/comfyui-tensorops
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Wan-VACE-Prep
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-various
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-WanAnimatePreprocess
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_LMStudio_EasyQuery
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_essentials
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyMath
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-custom-scripts
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-sam3
0.0 seconds: /home/aa/ComfyUI/custom_nodes/steerable-motion
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-multiband
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-frame-interpolation
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-SAM3DBody
0.0 seconds (IMPORT FAILED): /home/aa/ComfyUI/custom_nodes/ComfyUI-SDPose-OOD
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-dream-video-batches
0.0 seconds: /home/aa/ComfyUI/custom_nodes/vnccs
0.0 seconds: /home/aa/ComfyUI/custom_nodes/basic_data_handling
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Multiband
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_VNCCS_Utils
0.0 seconds: /home/aa/ComfyUI/custom_nodes/rgthree-comfy
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_essentials
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MelBandRoFormer
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-MotionCapture
0.0 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_controlnet_aux
0.0 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-LTXVideo
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-KJNodes
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-TRELLIS2
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI_DSS_Wrapper
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfy-mtb
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui_nvidia_rtx_nodes
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-videohelpersuite
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-impact-pack
0.1 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper
0.2 seconds: /home/aa/ComfyUI/custom_nodes/tts_audio_suite
0.3 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
0.3 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-geometrypack
0.6 seconds: /home/aa/ComfyUI/custom_nodes/seedvr2_videoupscaler
0.6 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-GeometryPack
0.7 seconds: /home/aa/ComfyUI/custom_nodes/was-ns
0.9 seconds: /home/aa/ComfyUI/custom_nodes/ComfyUI-HyMotion
1.7 seconds: /home/aa/ComfyUI/custom_nodes/comfyui-easy-use
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Starting server
To see the GUI go to: http://0.0.0.0:8189
To see the GUI go to: http://[::]:8189
FETCH ComfyRegistry Data: 10/130
FETCH ComfyRegistry Data: 15/130
FETCH ComfyRegistry Data: 20/130
FETCH ComfyRegistry Data: 25/130
FETCH ComfyRegistry Data: 30/130
FETCH ComfyRegistry Data: 35/130
FETCH ComfyRegistry Data: 40/130
FETCH ComfyRegistry Data: 45/130
FETCH ComfyRegistry Data: 50/130
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
{"client": "<lmstudio.sync_api.Client object at 0x77124827f980>", "event": "Websocket handling thread started", "thread_id": "Thread-8"}
Error fetching models: LM Studio is not reachable at any default port. Is LM Studio running?
Error fetching models: Local API host port is not yet resolved.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
🔧 Settings endpoint called
🔧 Received settings: precision=auto, device=auto, vc_engine=chatterbox_23lang, cosyvoice_variant=RL
🎨 Step Audio EditX inline tags: precision=auto, device=auto
🔄 Voice restoration engine: chatterbox_23lang
FETCH ComfyRegistry Data: 55/130
FETCH ComfyRegistry Data: 60/130
FETCH ComfyRegistry Data: 65/130
FETCH ComfyRegistry Data: 70/130
FETCH ComfyRegistry Data: 75/130
FETCH ComfyRegistry Data: 80/130
FETCH ComfyRegistry Data: 85/130
FETCH ComfyRegistry Data: 90/130
FETCH ComfyRegistry Data: 95/130
FETCH ComfyRegistry Data: 100/130
FETCH ComfyRegistry Data: 105/130
FETCH ComfyRegistry Data: 110/130
FETCH ComfyRegistry Data: 115/130
FETCH ComfyRegistry Data: 120/130
FETCH ComfyRegistry Data: 125/130
FETCH ComfyRegistry Data: 130/130
got prompt
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
RTX Video Super Resolution is unavailable (NvVFX_Load failed: An otherwise unspecified error has occurred (code -1)). This is typically caused by a driver/NGX SDK version mismatch. On WSL2, update your Windows NVIDIA driver to the latest version and restart WSL. Falling back to bicubic upscaling.